{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SDGVMIGH4OJACK2OFLCCXQS5KU","short_pith_number":"pith:SDGVMIGH","schema_version":"1.0","canonical_sha256":"90cd5620c7e392012b4e2ac42bc25d550de85308ce4a5a268bae62300e79c040","source":{"kind":"arxiv","id":"2311.15548","version":1},"attestation_state":"computed","paper":{"title":"Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-fin.ST"],"primary_cat":"cs.CL","authors_text":"Haoqiang Kang, Xiao-Yang Liu","submitted_at":"2023-11-27T05:27:13Z","abstract_excerpt":"The hallucination issue is recognized as a fundamental deficiency of large language models (LLMs), especially when applied to fields such as finance, education, and law. Despite the growing concerns, there has been a lack of empirical investigation. In this paper, we provide an empirical examination of LLMs' hallucination behaviors in financial tasks. First, we empirically investigate LLM model's ability of explaining financial concepts and terminologies. Second, we assess LLM models' capacity of querying historical stock prices. Third, to alleviate the hallucination issue, we evaluate the eff"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.15548","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T05:27:13Z","cross_cats_sorted":["cs.AI","cs.LG","q-fin.ST"],"title_canon_sha256":"a9a0abf421b643a038089298d14824675f468be0783782ed178102538cd85692","abstract_canon_sha256":"43158b86d869d11dec67a0cc27a70a5ff145abd3ead8c0b49b88a70db1a1b168"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:05.732075Z","signature_b64":"0FKXliumU850lEIleXJf6sn3O2laY/xDd1NYAFK0f6YDntjBRQhjJu76O2Rb7NUraUG1X4NBGYBZxtWWoZygCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90cd5620c7e392012b4e2ac42bc25d550de85308ce4a5a268bae62300e79c040","last_reissued_at":"2026-07-05T07:17:05.731548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:05.731548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-fin.ST"],"primary_cat":"cs.CL","authors_text":"Haoqiang Kang, Xiao-Yang Liu","submitted_at":"2023-11-27T05:27:13Z","abstract_excerpt":"The hallucination issue is recognized as a fundamental deficiency of large language models (LLMs), especially when applied to fields such as finance, education, and law. Despite the growing concerns, there has been a lack of empirical investigation. In this paper, we provide an empirical examination of LLMs' hallucination behaviors in financial tasks. First, we empirically investigate LLM model's ability of explaining financial concepts and terminologies. Second, we assess LLM models' capacity of querying historical stock prices. Third, to alleviate the hallucination issue, we evaluate the eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15548","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.15548/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.15548","created_at":"2026-07-05T07:17:05.731622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15548v1","created_at":"2026-07-05T07:17:05.731622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15548","created_at":"2026-07-05T07:17:05.731622+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDGVMIGH4OJA","created_at":"2026-07-05T07:17:05.731622+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDGVMIGH4OJACK2O","created_at":"2026-07-05T07:17:05.731622+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDGVMIGH","created_at":"2026-07-05T07:17:05.731622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15893","citing_title":"BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06959","citing_title":"OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31064","citing_title":"Fighting Numerical Hallucinations via Data-centric Compilation for Online Financial QA","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00919","citing_title":"Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18762","citing_title":"ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16895","citing_title":"The Alpha Illusion: Reported Alpha from LLM Trading Agents Should Not Be Treated as Deployment Evidence","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2512.05929","citing_title":"LLM Harms: A Taxonomy and Discussion","ref_index":180,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04992","citing_title":"You Snooze, You Lose: Automatic Safety Alignment Restoration through Neural Weight Translation","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22843","citing_title":"Structure Guided Retrieval-Augmented Generation for Factual Queries","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12115","citing_title":"HTDC: Hesitation-Triggered Differential Calibration for Mitigating Hallucination in Large Vision-Language Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDGVMIGH4OJACK2OFLCCXQS5KU","json":"https://pith.science/pith/SDGVMIGH4OJACK2OFLCCXQS5KU.json","graph_json":"https://pith.science/api/pith-number/SDGVMIGH4OJACK2OFLCCXQS5KU/graph.json","events_json":"https://pith.science/api/pith-number/SDGVMIGH4OJACK2OFLCCXQS5KU/events.json","paper":"https://pith.science/paper/SDGVMIGH"},"agent_actions":{"view_html":"https://pith.science/pith/SDGVMIGH4OJACK2OFLCCXQS5KU","download_json":"https://pith.science/pith/SDGVMIGH4OJACK2OFLCCXQS5KU.json","view_paper":"https://pith.science/paper/SDGVMIGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15548&json=true","fetch_graph":"https://pith.science/api/pith-number/SDGVMIGH4OJACK2OFLCCXQS5KU/graph.json","fetch_events":"https://pith.science/api/pith-number/SDGVMIGH4OJACK2OFLCCXQS5KU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDGVMIGH4OJACK2OFLCCXQS5KU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDGVMIGH4OJACK2OFLCCXQS5KU/action/storage_attestation","attest_author":"https://pith.science/pith/SDGVMIGH4OJACK2OFLCCXQS5KU/action/author_attestation","sign_citation":"https://pith.science/pith/SDGVMIGH4OJACK2OFLCCXQS5KU/action/citation_signature","submit_replication":"https://pith.science/pith/SDGVMIGH4OJACK2OFLCCXQS5KU/action/replication_record"}},"created_at":"2026-07-05T07:17:05.731622+00:00","updated_at":"2026-07-05T07:17:05.731622+00:00"}